US11935010B2 - Intelligent subject line suggestions and reformulation - Google Patents
Intelligent subject line suggestions and reformulation Download PDFInfo
- Publication number
- US11935010B2 US11935010B2 US16/671,122 US201916671122A US11935010B2 US 11935010 B2 US11935010 B2 US 11935010B2 US 201916671122 A US201916671122 A US 201916671122A US 11935010 B2 US11935010 B2 US 11935010B2
- Authority
- US
- United States
- Prior art keywords
- subject line
- content
- topic
- suggestion
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active, expires
Links
- 238000000034 method Methods 0.000 claims abstract description 75
- 230000009471 action Effects 0.000 claims abstract description 22
- 239000013598 vector Substances 0.000 claims description 74
- 230000015654 memory Effects 0.000 claims description 19
- 238000001514 detection method Methods 0.000 claims description 2
- 230000004044 response Effects 0.000 claims description 2
- 239000000203 mixture Substances 0.000 description 13
- 238000004891 communication Methods 0.000 description 10
- 238000010801 machine learning Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 238000013459 approach Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000013500 data storage Methods 0.000 description 3
- 230000014509 gene expression Effects 0.000 description 3
- 238000003058 natural language processing Methods 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 229910052799 carbon Inorganic materials 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000003490 calendering Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 235000021179 potluck Nutrition 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/107—Computer-aided management of electronic mailing [e-mailing]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
- G06F18/2113—Selection of the most significant subset of features by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/174—Form filling; Merging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/258—Heading extraction; Automatic titling; Numbering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/274—Converting codes to words; Guess-ahead of partial word inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/42—Mailbox-related aspects, e.g. synchronisation of mailboxes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
Definitions
- Existing email applications and providers include features to assist and increase user productivity.
- An example of such a feature is in the form of a type ahead feature, where as a user begins to compose a word, phrase, or sentence, ghosted text representing a suggested set of letters, words, and/or phrases that complete the initial word, phrase, and/or sentence composition are presented to the user.
- a user may compose an email and an email application may provide a subject line suggestion upon initiating a send functionality.
- existing email application often lack advanced features for enhancing sender and recipient productivity.
- Subject lines in messages are attention grabbers and as such they are important to conveying information through email. Accordingly, there is a need to provide intelligence based assistance to one or more users not only composing and/or replying to emails, but also users acting as the recipient.
- a basic subject line may be suggested based on the content provided in an email composition form; in some examples, the subject line may be suggested based on an existing email thread utilizing one or more machine learning techniques.
- subject lines may be tailored and stylized with key elements that for example, highlight if there is “action required” by recipients; highlight if there is a deadline that recipients need to be aware of; highlight or make a user aware that a key attachment or link is being shared, for example, flight tickets, receipts, or links to important articles; and/or highlight key points and/or questions raised in the email.
- intelligent subject lines may be suggested for each message, even if a message has an existing subject line based on thread history. In some instances, a suggested subject line may be based on the topic and attributes of the current message in addition or instead of the message thread history.
- FIG. 1 illustrates one or more components of an intelligent email subject line suggestion and reformulation system together with email content in accordance with examples of the present disclosure.
- FIG. 2 illustrates one or more topic vectors in accordance with examples of the present disclosure.
- FIG. 3 A illustrates a first example of a template utilized to formulate an email subject line suggestion in accordance with examples of the present disclosure.
- FIG. 3 B illustrates a second example of a template utilized to formulate an email subject line suggestion in accordance with examples of the present disclosure.
- FIG. 3 C illustrates a third example of a template utilized to formulate an email subject line suggestion in accordance with examples of the present disclosure.
- FIG. 3 D illustrates a fourth example of a template utilized to formulate an email subject line suggestion in accordance with examples of the present disclosure.
- FIG. 4 illustrates details of an intelligent email subject line suggestion and reformulation module in accordance with examples of the present disclosure.
- FIG. 5 illustrates details of a system for formulating and suggesting one or more subject lines in accordance with examples of the present disclosure.
- FIG. 6 illustrates a first method in accordance with examples of the present disclosure.
- FIG. 7 illustrates a second method in accordance with examples of the present disclosure.
- FIG. 8 illustrates a third method in accordance with examples of the present disclosure.
- FIG. 9 illustrates a fourth method in accordance with examples of the present disclosure.
- FIG. 10 is a block diagram illustrating example physical components of a computing device with which aspects of the disclosure may be practiced
- FIG. 11 A is a simplified block diagram of a computing device with which aspects of the present disclosure may be practiced.
- FIG. 11 B is another are simplified block diagram of a mobile computing device with which aspects of the present disclosure may be practiced.
- FIG. 12 is a simplified block diagram of a distributed computing system in which aspects of the present disclosure may be practiced.
- FIG. 1 illustrates an example email composition window 100 in accordance with examples of the present disclosure.
- the email composition window 100 may generally be utilized by a user to compose an email, where a user may provide an address from which an email is sent in the sender field 102 , one or more recipient addresses in a recipient field 104 , one or more recipient addresses in the carbon copy field 106 , one or more recipient addresses in the blind carbon copy field 108 , and a subject in the subject line 110 .
- the email composition window 100 may further include email content 112 , where the email content 112 may include a portion of email content.
- the subject provided by the user in the subject line 110 may include a summary description of the portion of email content 112 .
- an intelligent email subject line suggestion and reformulation system 101 may generate a subject in place of or otherwise to be included as part of a subject provided by a user in the subject line 110 . More specifically, the intelligent email subject line suggestion and reformulation system 101 may provide a subject that is based on one or more portions of email content 112 . In some examples, the one or more portions of email content 112 may correspond to one or more characteristics identified in the email, such as but not limited to a commitment 114 by a user, a general request 116 , a statement of fact 124 , a specific request for information 118 , a general request for information 120 , and/or a request for time 122 . Of course, other characteristics may be determined by the intelligent email subject line suggestion and reformulation system 101 and may be utilized to formulate a subject for the subject line 110 .
- the intelligent email subject line suggestion and reformulation system 101 may identify key topics of an email and/or email thread. For example, if an email is composed regarding a first topic, a machine learning technique may determine unique terms, or unique vocabulary, specific to this email. That is, common phrases, such as pleasantries and greetings like “Hi, how are you doing?”, etc., may be identified and removed from the content of the email for purposes of determining one or more possible subjects.
- the composed email may be compared against a universe of emails, the universe of emails being specific to the user composing the email, specific to a group of users, and/or relying on email composition information for a general population of users.
- commonly used phrases specific to the user, specific to the group, and/or specific to the general population of users may be removed; such commonly used phrases may be removed from the email content 112 to generate unique vocabulary specific to the email being composed. Accordingly, the unique terms, tokens, and/or vocabulary elements may be determined. Given the unique terms, tokens, and/or vocabulary elements for the email, a most likely subject is determined.
- FIG. 2 depicts an example of subject line formulation in accordance with examples of the present disclosure. More specifically, a machine learning model may be employed to compose a subject based on the remaining unique terms 204 determined in the email.
- the unique terms 208 for a specific non-limiting example may include “Potluck,” “Friday,” and “User 3 ”.
- a first vector 212 may include a first combination of the unique terms
- a second vector 216 may include a second combination of unique terms
- a third vector 220 may include a third combination of key terms, etc.
- Each vector may then be scored against possible email subjects determine from the user's inbox and/or other users' inbox across an organization or corpus of user information.
- a vector 224 for example, having the highest score may be indicated as the most likely subject line.
- additional linking terms such as “this” and “at” may be added to a vector; such linking terms may be generated by the intelligent email subject line suggestion and reformulation system 101 and may be based on one or more natural language processing techniques, such as but not limited to tagging parts of speech, shallow parsing and/or chunking, constituency parsing, and dependency parsing.
- natural language processing techniques such as but not limited to tagging parts of speech, shallow parsing and/or chunking, constituency parsing, and dependency parsing.
- other natural language processing techniques may be employed to generate a subject based on the identified one or more tokens.
- the intelligent email subject line suggestion and reformulation system 101 may generate a subject based on one or more intents identified within the email content 112 .
- the subject line may also include information specific to one or more actions, such as but not limited to a request, question, and/or request for time commitment included in the email content 112 .
- email content 112 may include a commitment 114 , for example, “I will send this to you on Friday.”
- the email content 112 may include one or more general requests 116 , for example, “Can you send it to me on Monday?”
- the email content 112 may include one or more specific requests for information 118 , such as “What items should we send to client A?”
- the email content 112 may include a general request for information 120 , such as “I'm interested in learning about topic A, please send me additional information about topic A.”
- the email content 112 may include a request for time, such as “Can we meet for 5 minutes on Friday?”
- email content 112 may include content that is classified as a statement 122 , such as “Here is a list of items to be performed by October 1.”
- At least one non-limiting example for determining an intent may include vectorizing one or more portions of the email content and analyzing such portions with an intent classifier.
- the intent classifier may compare a vectorized portion of content with one or more known intents and/or actions.
- the classifier may rely upon any of a number of known approaches including but not limited to generalized linear models, support vector machines, nearest neighbors, decision trees and neural networks.
- an intent classifier vectorizes a portion of the email content and may perform a nearest neighbor algorithm comparison between the vectorized portion of email content and the one or more known intents.
- a nearest neighbor vector identifies the intent.
- an object classifier may be utilized to identify an object.
- the object classifier may work in the same or similar manner as the intent classifier.
- the classifier may rely upon any of a number of machine learning approaches including but not limited to any known generalized linear models, support vector machines, nearest neighbors, decision trees and neural networks.
- the object classifier may vectorize one or more object attributes which may include but is not limited to parsing the one or more portions of email content into parts of speech, extracting nouns or verbs, and matching to stored object data.
- the object classifier may determine the nearest match, by running a nearest neighbor algorithm comparison; the nearest neighbor may identify one or more objects that will be used as an object in the intent.
- one or more templates for use may be determined and a subject line 110 may be suggested and may include elements or objects from the one or more identified actions and/or statements in the email content 112 .
- a template may be defined and/or customized to a user, organization, or otherwise, and may include one or more slots that are to be filled based on the template and the information pertaining to an identified intent.
- one or more templates 304 may be matched to an identified request; for example, a first template 304 which may include the plurality of slots 308 associated with a request, topic, and deadline 312 .
- the intelligent email subject line suggestion and reformulation system 101 may identify information 316 to fill in or otherwise be placed into the one or more slots 308 / 312 . Accordingly, the intelligent email subject line suggestion and reformulation system 101 may generate a subject 320 corresponding to at least on intent identified in the email content 112 .
- one or more templates 324 may be matched to an identified request; for example, a fifth template 324 which may include the plurality of slots 328 associated with a statement, topic, and specific portion 332 specific to the topic.
- the intelligent email subject line suggestion and reformulation system 101 may identify information 336 to fill in or otherwise be placed into the one or more slots 332 / 328 . Accordingly, the intelligent email subject line suggestion and reformulation system 101 may generate a subject 340 corresponding to at least on intent identified in the email content 112 .
- one or more templates 344 may be matched to an identified request; for example, a seventh template 344 which may include the plurality of slots 348 associated with a request for time which includes a requestor, time duration, and date 352 .
- the intelligent email subject line suggestion and reformulation system 101 may identify information 356 to fill in or otherwise be placed into the one or more slots 352 / 348 . Accordingly, the intelligent email subject line suggestion and reformulation system 101 may generate a subject 360 corresponding to at least on intent identified in the email content 112 .
- one or more templates 364 may be matched to an identified request; for example, a seventeenth template 364 which may include the plurality of slots 368 associated with a request for content and topic 372 .
- the intelligent email subject line suggestion and reformulation system 101 may identify information 376 to fill in or otherwise be placed into the one or more slots 372 / 368 . Accordingly, the intelligent email subject line suggestion and reformulation system 101 may generate a subject 380 corresponding to at least on intent identified in the email content 112 .
- the intelligent email subject line suggestion and reformulation system 412 which may be the same as or similar to the intelligent email subject line suggestion and reformulation system 101 , and may include an intelligent email subject line suggestion and reformulation module 416 which may generate a proposed subject and/or cause to be displayed to a user the proposed subject to a display for a user.
- the intelligent email subject line suggestion and reformulation system 412 may include a subject term generator 420 , an intent identifier 424 , a subject line formulator 452 , and storage 456 .
- the subject term generator 420 may be utilized to generate one or more vectors, such as vectors 212 - 220 for example.
- the subject term generator 420 may include a content parser 428 , key term identifier 432 , and the term vector evaluator 436 .
- the content parser may receive email content, such as email content 112 and parse such content to identify one or more characteristics of the email content 112 .
- at least one characteristic may be indicative of an existing thread in the email content 112 .
- the at least one characteristic may be indicative of an existing subject field and/or a recipient field.
- the key term identifier 432 may utilize content provided by the content parser 428 and remove content that is determined to be common to previous emails composed by the user and/or previous emails associated with a corpus of email content. The key term identifier 432 may then provide the key terms to the term vector evaluator 436 , where the term vector evaluator may score differing combinations, including ordered combinations and combinations including additional linking words, to identify a highest scored vector. The highest scored vector may then be provided to the subject line formulator 452 .
- the intent identifier 424 may include a content parser 440 , an intent extractor 444 , and a template selector 448 .
- the intent identifier 424 may be utilized to determine an intent of the email content, for example, email content 112 .
- An intent of email content may include but is not limited to an action, a request for information, a request for time, a statement, a commitment, a specific or general request for information, etc.
- the content parser 440 may receive email content, such as email content 112 and parse such content to identify one or more characteristics of the email content 112 and/or mark one or more portions of the email content indicative of or otherwise seeming to express an intent.
- At least one characteristic may be indicative of a new sentence, phrase, and/or word which may indicate the beginning of a portion of the email content that includes the intent.
- the at least one characteristic may be indicative of a question, statement, exclamation, or the attachment of a document and/or file.
- an intent and/or object may be determined in a manner described above utilizing one or more machine learning approaches.
- the intent extractor 444 may evaluate one or more portions of email content provided by the content parser 440 and extract an intent from such portions. In some examples, one or more machine learning approaches described above may be utilized. In some examples, one or more natural language processing techniques may be utilized to identify an intent of the one or more portions of email content. Based on the determined intent, a template, such as one or more of the previously described templates including, but not limited to templates 304 , 324 , 344 , and 364 , may be selected. One or more of the templates may be specific to a user, and organization, and/or other grouping of users. The template selector 448 may further populate one or more slots of the template as previously described.
- the subject line formulator 452 may utilize the selected template to formulate a suggested subject line. In some instances, the subject line formulator 452 may utilize one or more terms from the subject term generator together with the selected template to formulate a suggested subject line. In accordance with examples of the present disclosure, the storage 456 may store the formulated subject line, one or more of the term vectors, the email content 112 , one or more extracted intents, and/or one or more of the templates, selected or otherwise.
- an email composed by a user may have multiple intents, for example multiple factual statements and/or one or more commitments.
- each of the intents may be identified, ranked, and one or more of the multiple intents may be selected based on which intent has been statistically determined to be most appropriate.
- the multiple intents may indicate that a subject line is to be generalized to accommodate the multiple intents.
- the subject line suggestion may be generalized to “info for budget FY20” for example, where the common element or object of budget and/or FY20 is identified and the first portion, second portion, and third portion belong to a same category or otherwise classified as being the same or similar.
- a type of intent may take precedence over another type of intent.
- the subject line suggestion may include the request instead of the commitment.
- an email portion may include three facts and one request; in such an instance, the request may take precedence and may be included in the suggested subject line instead of the three facts.
- the determination and/or selection of which intent and/or object should be included in a suggested subject line may be based on heuristics and/or user preference.
- the subject line formulator 452 may preserve a conversation identifier associated with the email content. For example, in an instant where a user replies to an existing email or email thread, the subject of the email thread may be modified or replaced by the subject line formulator 452 ; however, in order to preserve the email thread, or conversation, where threads, or conversations, may be grouped by a common subject line, the intelligent email subject line suggestion and reformulation system 412 may preserve a conversation identifier, in metadata for example, and the conversation identifier may be included as part of the email message.
- FIG. 5 depicts an example system 500 for formulating and suggesting an email subject line in accordance with examples of the present disclosure.
- the system 500 may include an email subject line suggestion and reformulation system 502 which may be the same as or similar to the email subject line suggestion and reformulation system 412 previously described.
- An indication that a user is composing an email may be received at 504 , where such indication may correspond to email content, or a portion of email content, being received in an email composition window, such as the email composition window 100 .
- the indication received at 504 may correspond to a user selecting a send email option, button, and/or control and/or correspond to a period of inactivity, wherein the period of inactivity may correspond to a period of inactivity in the email composition window 100 for example.
- the email content, or portion of email content may be compared to emails previously composed by the user to determine common portions of email content that can be removed from the email content, or portion of email content.
- a key term vector may be generated as previously described and may rely on key terms of the email content, or portion of email content, remaining after common portions have been removed and/or a corpus of email, such as public email store 512 , utilized to score and rank on or more key term vectors. Accordingly, at 516 , the term vector having a highest score for instance, may be generated as 518 .
- the email content, or portion of email content may be parsed such that an intent of the email content, or portion of email content may be determined.
- the email content, or portion of email content may include a question or action and such question or action may be considered an “intent” of the email and may be extracted at 520 yielding an intent 510 .
- the intent may be utilized to select a template and the key term vector 518 may be utilized to populate at least a portion of the template—that is, one or more slots may be populated utilizing one or more key terms from the key term vector 518 .
- a subject line may be formulated.
- the subject line 110 for example of the email composition window 100 may be populated utilizing the formulated subject line.
- the formulated subject line may be presented to a user prior to the formulated subject line being provided to or otherwise presented at the subject line 110 of the email composition window 100 .
- a user may be able to select the formulated subject line or deny the use of the formulated subject line; a selected formulated subject line may be presented in the subject line 110 whereas denying the formulated subject line may cause a subject line, if present, to remain in the subject line 110 .
- the portions within the area 522 may be performed by one or more machine learning approaches discussed above; that is, 522 may be a machine learning model trained to suggest one or more subject lines, where such model may be trained for one or more users and/or one or more organizations. In some cases, the model is consistently retrained based on the acceptance and/or denial of a suggested subject line.
- FIG. 6 depicts details of a method 600 for suggesting and formulating an intelligent subject line in accordance with examples of the present disclosure.
- a general order for the steps of the method 600 is shown in FIG. 6 .
- the method 600 starts at 604 and ends at 620 .
- the method 600 may include more or fewer steps or may arrange the order of the steps differently than those shown in FIG. 6 .
- the method 600 can be executed as a set of computer-executable instructions executed by a computer system and encoded or stored on a computer readable medium. Further, the method 600 can be performed by gates or circuits associated with a processor, Application Specific Integrated Circuit (ASIC), a field programmable gate array (FPGA), a system on chip (SOC), or other hardware device.
- ASIC Application Specific Integrated Circuit
- FPGA field programmable gate array
- SOC system on chip
- the method 600 starts at 604 , where an indication that a user is composing an email is received. For example, an indication that a user selected a send email option, command, button or otherwise may be received and/or an indication may be received corresponding to a period of inactivity. Based on the received indication, the method may proceed to 608 where email content, or a portion of email content, may be parsed to identify one or more topics of the email content and/or portion of email content. Based on the one or more topics, a topic vector may be determined as previously described. The method 600 may proceed to 612 where an intent of the email may be identified. For example, the intent may correspond to an action, a request for content, request for specific content, a question, and/or a request for time.
- a new subject line may be formulated based on the previously identified topic vector and the identified, or determined, intent. For example, and as previously described, a template may be selected based on intent; such template may be populated utilizing one or more of the topic vectors of 608 for example. At 616 , one or more slots of the template may be filled with one or more words or combination of words present in the topic vector.
- the method 600 may then proceed to 620 , where the newly formulated subject line may be presented to the user.
- the method 600 may be executed multiple times. Accordingly, at a first time, a first newly formulated subject may be presented to a user. At a second time, a second newly formulated subject may be presented to the user. Accordingly, the method 600 may execute in real-time and/or in near real-time.
- FIG. 7 depicts details of a method 700 for identifying and/or determining possible topic vectors in accordance with examples of the present disclosure.
- a general order for the steps of the method 700 is shown in FIG. 7 .
- the method 700 starts at 704 and ends at 724 .
- the method 700 may include more or fewer steps or may arrange the order of the steps differently than those shown in FIG. 7 .
- the method 700 can be executed as a set of computer-executable instructions executed by a computer system and encoded or stored on a computer readable medium. Further, the method 700 can be performed by gates or circuits associated with a processor, Application Specific Integrated Circuit (ASIC), a field programmable gate array (FPGA), a system on chip (SOC), or other hardware device.
- ASIC Application Specific Integrated Circuit
- FPGA field programmable gate array
- SOC system on chip
- the method 700 starts at 704 , where email content may be received.
- a portion of email content may correspond to the email content 112 and/or content of the subject line 110 .
- commonalities between the email content received at 704 and email content corresponding to an existing corpus of email may be determined and such commonalities may be removed, leaving unique vocabulary and/or topic content.
- the existing corpus of email may correspond to a personal email store where user composed emails may be utilized as a source of identifying common expressions and common vocabulary used in prior email compositions.
- the existing corpus of email may correspond to a public email store where emails composed from multiple users may be utilized as a source of identifying common expressions and common vocabulary.
- the common vocabulary and/or common expressions may be removed from the email content received at 704 .
- each new possible topic vector may be scored utilizing an existing corpus of email content.
- the existing corpus of email content may be the same as or similar to the existing corpus of email content utilized at 708 .
- the existing corpus of email content may be different from the existing corpus of email content utilized at 708 .
- a topic vector representing a most likely ordering of topics may be selected. For example, the topic vector having a highest score may be selected. The selected topic vector may then be utilized to generate a new subject line, such as in 616 as previously described.
- FIG. 8 depicts details of a method 800 for determining an intent from email content in accordance with examples of the present disclosure.
- a general order for the steps of the method 800 is shown in FIG. 8 .
- the method 800 starts at 804 and ends at 816 .
- the method 800 may include more or fewer steps or may arrange the order of the steps differently than those shown in FIG. 8 .
- the method 800 can be executed as a set of computer-executable instructions executed by a computer system and encoded or stored on a computer readable medium. Further, the method 800 can be performed by gates or circuits associated with a processor, Application Specific Integrated Circuit (ASIC), a field programmable gate array (FPGA), a system on chip (SOC), or other hardware device.
- ASIC Application Specific Integrated Circuit
- FPGA field programmable gate array
- SOC system on chip
- the method 800 starts at 804 , where email content may be received.
- the email content may correspond to a portion of email content 112 , content of the subject line 110 , and/or content of one or more fields described with respect to FIG. 1 .
- one or more characteristics of the email may be extracted and/or determined.
- a portion of the email content 112 may indicate that an action is required on the part of the email sender (user composing the email). Accordingly, a characteristic may indicate that an action is to be performed; accordingly, an intent of the email may be to provide the recipient with an action.
- email content 112 may indicate that a question is being presented to an email recipient. Accordingly, a characteristic of the email may indicate that an intent of the email is to present a question.
- FIG. 9 depicts details of another method 900 for providing an email subject line suggestion.
- a general order for the steps of the method 900 is shown in FIG. 9 .
- the method 900 starts at 904 and ends at 916 .
- the method 900 may include more or fewer steps or may arrange the order of the steps differently than those shown in FIG. 9 .
- the method 900 can be executed as a set of computer-executable instructions executed by a computer system and encoded or stored on a computer readable medium. Further, the method 900 can be performed by gates or circuits associated with a processor, Application Specific Integrated Circuit (ASIC), a field programmable gate array (FPGA), a system on chip (SOC), or other hardware device.
- ASIC Application Specific Integrated Circuit
- FPGA field programmable gate array
- SOC system on chip
- the method 900 starts at 904 , where email content may be received.
- the email content may correspond to a portion of the email content 112 , content of the subject line 110 , and/or content of one or more fields described with respect to FIG. 1 .
- an email containing content that closely matches the received email content may be identified and/or determined at 908 .
- a user may have sent an email to a first recipient; where the email to the first recipient includes the same or similar information to be sent to a second separate recipient. Accordingly, the email sent to the first recipient may be determined/identified.
- the subject of the identified/determined email may be copied.
- the subject line of the email going to the first recipient may be utilized as a template, or base, for formulating the subject line. Accordingly, at 916 , the copied subject line may be updated/populated utilizing one or more topics identified from a topic vector as previously described.
- FIGS. 10 - 12 and the associated descriptions provide a discussion of a variety of operating environments in which aspects of the disclosure may be practiced.
- the devices and systems illustrated and discussed with respect to FIGS. 10 - 12 are for purposes of example and illustration and are not limiting of a vast number of computing device configurations that may be utilized for practicing aspects of the disclosure, described herein.
- FIG. 10 is a block diagram illustrating physical components (e.g., hardware) of a computing device 1000 with which aspects of the disclosure may be practiced.
- the computing device components described below may be suitable for the computing devices described above.
- the computing device 1000 may include at least one processing unit 1002 and a system memory 1004 .
- the system memory 1004 may comprise, but is not limited to, volatile storage (e.g., random access memory), non-volatile storage (e.g., read-only memory), flash memory, or any combination of such memories.
- the system memory 1004 may include an operating system 1005 and one or more program modules 1006 suitable for running software application 1020 , such as one or more components supported by the systems described herein. As examples, system memory 1004 may store the intelligent email subject line suggestion and reformulation module 1024 .
- the operating system 1005 for example, may be suitable for controlling the operation of the computing device 1000 .
- FIG. 10 This basic configuration is illustrated in FIG. 10 by those components within a dashed line 1008 .
- the computing device 1000 may have additional features or functionality.
- the computing device 1000 may also include additional data storage devices (removable and/or non-removable) such as, for example, magnetic disks, optical disks, or tape.
- additional storage is illustrated in FIG. 10 by a removable storage device 1009 and a non-removable storage device 1010 .
- program modules 1006 may perform processes including, but not limited to, the aspects, as described herein.
- Other program modules may include electronic mail and contacts applications, word processing applications, spreadsheet applications, database applications, slide presentation applications, drawing or computer-aided application programs, etc.
- embodiments of the disclosure may be practiced in an electrical circuit comprising discrete electronic elements, packaged or integrated electronic chips containing logic gates, a circuit utilizing a microprocessor, or on a single chip containing electronic elements or microprocessors.
- embodiments of the disclosure may be practiced via a system-on-a-chip (SOC) where each or many of the components illustrated in FIG. 10 may be integrated onto a single integrated circuit.
- SOC system-on-a-chip
- Such an SOC device may include one or more processing units, graphics units, communications units, system virtualization units and various application functionality all of which are integrated (or “burned”) onto the chip substrate as a single integrated circuit.
- the functionality, described herein, with respect to the capability of client to switch protocols may be operated via application-specific logic integrated with other components of the computing device 1000 on the single integrated circuit (chip).
- Embodiments of the disclosure may also be practiced using other technologies capable of performing logical operations such as, for example, AND, OR, and NOT, including but not limited to mechanical, optical, fluidic, and quantum technologies.
- embodiments of the disclosure may be practiced within a general purpose computer or in any other circuits or systems.
- the computing device 1000 may also have one or more input device(s) 1012 such as a keyboard, a mouse, a pen, a sound or voice input device, a touch or swipe input device, etc.
- the output device(s) 1014 such as a display, speakers, a printer, etc. may also be included.
- the aforementioned devices are examples and others may be used.
- the computing device 1000 may include one or more communication connections 1016 allowing communications with other computing devices 1050 . Examples of suitable communication connections 1016 include, but are not limited to, radio frequency (RF) transmitter, receiver, and/or transceiver circuitry; universal serial bus (USB), parallel, and/or serial ports.
- RF radio frequency
- USB universal serial bus
- Computer readable media may include computer storage media.
- Computer storage media may include volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information, such as computer readable instructions, data structures, or program modules.
- the system memory 1004 , the removable storage device 1009 , and the non-removable storage device 1010 are all computer storage media examples (e.g., memory storage).
- Computer storage media may include RAM, ROM, electrically erasable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other article of manufacture which can be used to store information and which can be accessed by the computing device 1000 . Any such computer storage media may be part of the computing device 1000 .
- Computer storage media does not include a carrier wave or other propagated or modulated data signal.
- Communication media may be embodied by computer readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave or other transport mechanism, and includes any information delivery media.
- modulated data signal may describe a signal that has one or more characteristics set or changed in such a manner as to encode information in the signal.
- communication media may include wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, radio frequency (RF), infrared, and other wireless media.
- RF radio frequency
- FIGS. 11 A and 11 B illustrate a mobile computing device 1100 , for example, a mobile telephone, a smart phone, wearable computer (such as a smart watch), a tablet computer, a laptop computer, and the like, with which embodiments of the disclosure may be practiced.
- the client may be a mobile computing device.
- FIG. 11 A one aspect of a mobile computing device 1100 for implementing the aspects is illustrated.
- the mobile computing device 1100 is a handheld computer having both input elements and output elements.
- the mobile computing device 1100 typically includes a display 1105 and one or more input buttons 1110 that allow the user to enter information into the mobile computing device 1100 .
- the display 1105 of the mobile computing device 1100 may also function as an input device (e.g., a touch screen display).
- an optional side input element 1115 allows further user input.
- the side input element 1115 may be a rotary switch, a button, or any other type of manual input element.
- mobile computing device 1100 may incorporate more or less input elements.
- the display 1105 may not be a touch screen in some embodiments.
- the mobile computing device 1100 is a portable phone system, such as a cellular phone.
- the mobile computing device 1100 may also include an optional keypad 1135 .
- Optional keypad 1135 may be a physical keypad or a “soft” keypad generated on the touch screen display.
- the output elements include the display 1105 for showing a graphical user interface (GUI), a visual indicator 820 (e.g., a light emitting diode), and/or an audio transducer 1125 (e.g., a speaker).
- GUI graphical user interface
- the mobile computing device 1100 incorporates a vibration transducer for providing the user with tactile feedback.
- the mobile computing device 1100 incorporates input and/or output ports, such as an audio input (e.g., a microphone jack), an audio output (e.g., a headphone jack), and a video output (e.g., a HDMI port) for sending signals to or receiving signals from an external device.
- FIG. 11 B is a block diagram illustrating the architecture of one aspect of a mobile computing device. That is, the mobile computing device 1100 can incorporate a system (e.g., an architecture) 1102 to implement some aspects.
- the system 1102 is implemented as a “smart phone” capable of running one or more applications (e.g., browser, e-mail, calendaring, contact managers, messaging clients, games, and media clients/players).
- the system 1102 is integrated as a computing device, such as an integrated personal digital assistant (PDA) and wireless phone.
- PDA personal digital assistant
- One or more application programs 1166 may be loaded into the memory 1162 and run on or in association with the operating system 1164 .
- Examples of the application programs include phone dialer programs, e-mail programs, personal information management (PIM) programs, word processing programs, spreadsheet programs, Internet browser programs, messaging programs, and so forth.
- the system 1102 also includes a non-volatile storage area 1168 within the memory 1162 .
- the non-volatile storage area 1168 may be used to store persistent information that should not be lost if the system 1102 is powered down.
- the application programs 1166 may use and store information in the non-volatile storage area 1168 , such as e-mail or other messages used by an e-mail application, and the like.
- a synchronization application (not shown) also resides on the system 1102 and is programmed to interact with a corresponding synchronization application resident on a host computer to keep the information stored in the non-volatile storage area 1168 synchronized with corresponding information stored at the host computer.
- other applications may be loaded into the memory 1162 and run on the mobile computing device 1100 described herein (e.g., search engine, extractor module, relevancy ranking module, answer scoring module, etc.).
- the system 1102 has a power supply 1170 , which may be implemented as one or more batteries.
- the power supply 1170 might further include an external power source, such as an AC adapter or a powered docking cradle that supplements or recharges the batteries.
- the system 1102 may also include a radio interface layer 1172 that performs the function of transmitting and receiving radio frequency communications.
- the radio interface layer 1172 facilitates wireless connectivity between the system 1102 and the “outside world,” via a communications carrier or service provider. Transmissions to and from the radio interface layer 1172 are conducted under control of the operating system 1164 . In other words, communications received by the radio interface layer 1172 may be disseminated to the application programs 1166 via the operating system 1164 , and vice versa.
- the visual indicator 1120 may be used to provide visual notifications, and/or an audio interface 1174 may be used for producing audible notifications via the audio transducer 1125 .
- the visual indicator 1120 is a light emitting diode (LED) and the audio transducer 1125 is a speaker.
- LED light emitting diode
- the LED may be programmed to remain on indefinitely until the user takes action to indicate the powered-on status of the device.
- the audio interface 1174 is used to provide audible signals to and receive audible signals from the user.
- the audio interface 1174 may also be coupled to a microphone to receive audible input, such as to facilitate a telephone conversation.
- the microphone may also serve as an audio sensor to facilitate control of notifications, as will be described below.
- the system 1102 may further include a video interface 1176 that enables an operation of an on-board camera 1130 to record still images, video stream, and the like.
- a mobile computing device 1100 implementing the system 1102 may have additional features or functionality.
- the mobile computing device 1100 may also include additional data storage devices (removable and/or non-removable) such as, magnetic disks, optical disks, or tape.
- additional storage is illustrated in FIG. 11 B by the non-volatile storage area 1168 .
- Data/information generated or captured by the mobile computing device 1100 and stored via the system 1102 may be stored locally on the mobile computing device 1100 , as described above, or the data may be stored on any number of storage media that may be accessed by the device via the radio interface layer 1172 or via a wired connection between the mobile computing device 1100 and a separate computing device associated with the mobile computing device 1100 , for example, a server computer in a distributed computing network, such as the Internet.
- a server computer in a distributed computing network such as the Internet.
- data/information may be accessed via the mobile computing device 1100 via the radio interface layer 1172 or via a distributed computing network.
- data/information may be readily transferred between computing devices for storage and use according to well-known data/information transfer and storage means, including electronic mail and collaborative data/information sharing systems.
- FIG. 12 illustrates one aspect of the architecture of a system for processing data received at a computing system from a remote source, such as a personal computer 1204 , tablet computing device 1206 , or mobile computing device 1208 , as described above.
- Content displayed at server device 1202 may be stored in different communication channels or other storage types.
- various documents may be stored using a directory service 1222 , a web portal 1224 , a mailbox service 1226 , an instant messaging store 1228 , or a social networking site 1230 .
- An Intelligent Email Subject Line Suggestion and Reformulation Module 1220 may be employed by a client that communicates with server device 1202 , and/or the Intelligent Email Subject Line Suggestion and Reformulation Module 1221 may be employed by server device 1202 .
- the server device 1202 may provide data to and from a client computing device such as a personal computer 1204 , a tablet computing device 1206 and/or a mobile computing device 1208 (e.g., a smart phone) through a network 1215 .
- a client computing device such as a personal computer 1204 , a tablet computing device 1206 and/or a mobile computing device 1208 (e.g., a smart phone) through a network 1215 .
- the computer system described above may be embodied in a personal computer 1204 , a tablet computing device 1206 and/or a mobile computing device 1208 (e.g., a smart phone). Any of these embodiments of the computing devices may obtain content from the store 1216 , in addition to receiving graphical data useable to be
- FIG. 12 illustrates an exemplary mobile computing device 1200 that may execute one or more aspects disclosed herein.
- the aspects and functionalities described herein may operate over distributed systems (e.g., cloud-based computing systems), where application functionality, memory, data storage and retrieval and various processing functions may be operated remotely from each other over a distributed computing network, such as the Internet or an intranet.
- distributed systems e.g., cloud-based computing systems
- application functionality, memory, data storage and retrieval and various processing functions may be operated remotely from each other over a distributed computing network, such as the Internet or an intranet.
- User interfaces and information of various types may be displayed via on-board computing device displays or via remote display units associated with one or more computing devices. For example, user interfaces and information of various types may be displayed and interacted with on a wall surface onto which user interfaces and information of various types are projected.
- Interaction with the multitude of computing systems with which embodiments of the invention may be practiced include, keystroke entry, touch screen entry, voice or other audio entry, gesture entry where an associated computing device is equipped with detection (e.g., camera) functionality for capturing and interpreting user gestures for controlling the functionality of the computing device, and the like.
- detection e.g., camera
- a system including a processor and memory.
- the memory may store instructions that, when executed by the processor, cause the system to perform a set of operations.
- the set of operations may include receiving content corresponding to one or more portions of an email, determining, based on the one or more portions of the email, one or more email topics, determining, based on the one or more portions of the email, at least one intent of the email, formulating a subject line suggestion based on the one or more email topics and the at least one intent of the email, and causing the subject line suggestion to be output to a display device.
- At least one aspect of the above example includes where determining the one or more email topics includes comparing the content to a plurality of emails sent by a user to identify portions common to the received content and at least one email of the plurality of emails, removing the common portions from the received content, and generating a plurality of topic vectors based on the content remaining after removing the common portions.
- the set of operations includes ranking each topic vector of the plurality of topic vectors based on a similarity to one or more topic vectors provided from a corpus of email, and formulating the subject line suggestion based on a topic vector and ranking.
- At least one aspect of the above example includes where the intent is at least one of a question, an action, a request for time, or a request for information. At least one aspect of the above example includes where the one or more portions of the email include the subject line. At least one aspect of the above example includes where the set of operations includes: selecting a subject line template based on the determined intent of the email, and populating one or more slots of the template utilizing the determined one or more email topics to generate the subject line suggestion.
- At least one aspect of the above example includes where the set of operations includes: identifying an email sent by a user that is similar to the received content corresponding to one or more portions of the email, extracting a subject line as a subject line suggestion from the email sent by the user, and updating one or more topics of the subject line suggestions utilizing one or more email topics. At least one aspect of the above example includes where the set of operations includes replacing an existing subject line of the email with the subject line suggestion.
- a method may include receiving content corresponding to one or more portions of an email, determining, based on a first portion of content of the one or more portions of the email, one or more email topics, determining, based on a second portion of content of the one or more portions of the email, at least one intent of the email, formulating a subject line suggestion based on the one or more email topics and the at least one intent of the email, and causing the subject line suggestion to be output to a display device.
- At least one aspect of the above method may include where the intent is at least one of a question, an action, a request for time, or a request for information. At least one aspect of the above method may include where the one or more portions of the email include the subject line. At least one aspect of the above method may include selecting a subject line template based on the determined intent of the email, and populating one or more slots of the template utilizing the determined one or more email topics to generate the subject line suggestion.
- At least one aspect of the above method may include identifying an email sent by a user that is similar to the second portion of content of the one or more portions of the email, extracting a subject line from the email sent by the user as a subject line suggestion from the email sent by the user, and updating one or more topics of the subject line suggestion utilizing the one or more email topics.
- At least one aspect of the above method may include receiving content corresponding to one or more portions of an email in response to receiving an indication that a user is composing an email.
- At least one aspect of the above method may include replacing an existing subject line of the email with the subject line suggestion.
- a method may include receiving content corresponding to one or more portions of an email, identifying an email sent by the user that includes content similar to a first portion of content of the one or more portions of the email, extracting a subject line from the email sent by the user as a subject line suggestion, updating one or more topics of the subject line suggestion, and causing the subject line suggestion to be output to a display device.
- At least one aspect of the above example may include determining, based on a first portion of content corresponding to one or more portions of the email, one or more email topics, and updating the subject line suggestion based on the determined one or more topics.
- At least one aspect of the above example includes replacing an existing subject line of the email with the subject line suggestion.
Abstract
Description
Claims (18)
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US16/671,122 US11935010B2 (en) | 2019-10-31 | 2019-10-31 | Intelligent subject line suggestions and reformulation |
CN202080075845.0A CN114631094A (en) | 2019-10-31 | 2020-10-09 | Intelligent e-mail headline suggestion and remake |
PCT/US2020/054894 WO2021086573A1 (en) | 2019-10-31 | 2020-10-09 | Intelligent e-mail subject line suggestions and reformulation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US16/671,122 US11935010B2 (en) | 2019-10-31 | 2019-10-31 | Intelligent subject line suggestions and reformulation |
Publications (2)
Publication Number | Publication Date |
---|---|
US20210133287A1 US20210133287A1 (en) | 2021-05-06 |
US11935010B2 true US11935010B2 (en) | 2024-03-19 |
Family
ID=73030252
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/671,122 Active 2041-06-07 US11935010B2 (en) | 2019-10-31 | 2019-10-31 | Intelligent subject line suggestions and reformulation |
Country Status (3)
Country | Link |
---|---|
US (1) | US11935010B2 (en) |
CN (1) | CN114631094A (en) |
WO (1) | WO2021086573A1 (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11301616B1 (en) * | 2020-10-09 | 2022-04-12 | Docusign, Inc. | Using machine learning to predict performance of secure documents |
US11710000B1 (en) * | 2022-06-13 | 2023-07-25 | Capital One Services, Llc | Email rewrite and reorganization |
US20240005365A1 (en) * | 2022-06-30 | 2024-01-04 | Constant Contact, Inc. | Email Subject Line Generation Method |
Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050228790A1 (en) * | 2004-04-12 | 2005-10-13 | Christopher Ronnewinkel | Coherent categorization scheme |
US20070250576A1 (en) | 2006-04-21 | 2007-10-25 | Shruti Kumar | Method and system for automatically providing an abstract of a response message in a subject line of the response message |
US20090055481A1 (en) | 2007-08-20 | 2009-02-26 | International Business Machines Corporation | Automatically generated subject recommendations for email messages based on email message content |
US20090106650A1 (en) | 2007-10-23 | 2009-04-23 | International Business Machines Corporation | Customizing email subjects for subscription generated email messages |
US20110154221A1 (en) | 2009-12-22 | 2011-06-23 | International Business Machines Corporation | Subject suggestion based on e-mail recipients |
US20120110432A1 (en) * | 2010-10-29 | 2012-05-03 | Microsoft Corporation | Tool for Automated Online Blog Generation |
US20130346511A1 (en) * | 2012-06-20 | 2013-12-26 | Comcast Cable Communications, Llc | Life management services |
US8645430B2 (en) | 2008-10-20 | 2014-02-04 | Cisco Technology, Inc. | Self-adjusting email subject and email subject history |
US20140289344A1 (en) | 2013-03-07 | 2014-09-25 | Jeff CALHOUN | Digital notification enhancement system |
US20150058426A1 (en) | 2013-08-23 | 2015-02-26 | International Business Machines Corporation | System and method for automatically generating email subject lines |
US9092742B1 (en) | 2014-05-27 | 2015-07-28 | Insidesales.com | Email optimization for predicted recipient behavior: suggesting changes in an email to increase the likelihood of an outcome |
US20160196561A1 (en) * | 2015-01-06 | 2016-07-07 | Adobe Systems Incorporated | Organizing and classifying social media conversations to improve customer service |
US20170177715A1 (en) * | 2015-12-21 | 2017-06-22 | Adobe Systems Incorporated | Natural Language System Question Classifier, Semantic Representations, and Logical Form Templates |
US20170295118A1 (en) * | 2016-04-11 | 2017-10-12 | Yahoo!, Inc. | Content subject suggestions |
US20190197107A1 (en) * | 2017-12-22 | 2019-06-27 | Microsoft Technology Licensing, Llc | AI System to Determine Actionable Intent |
US20200019609A1 (en) * | 2018-07-13 | 2020-01-16 | Asapp, Inc. | Suggesting a response to a message by selecting a template using a neural network |
EP3654258A1 (en) * | 2018-11-14 | 2020-05-20 | KBC Groep NV | Automated electronic mail assistant |
US20200193380A1 (en) * | 2018-12-14 | 2020-06-18 | International Business Machines Corporation | Detection and categorization of electronic communications |
US20210083998A1 (en) * | 2019-09-12 | 2021-03-18 | International Business Machines Corporation | Machine Logic Rules to Enhance Email Distribution |
-
2019
- 2019-10-31 US US16/671,122 patent/US11935010B2/en active Active
-
2020
- 2020-10-09 CN CN202080075845.0A patent/CN114631094A/en active Pending
- 2020-10-09 WO PCT/US2020/054894 patent/WO2021086573A1/en active Application Filing
Patent Citations (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050228790A1 (en) * | 2004-04-12 | 2005-10-13 | Christopher Ronnewinkel | Coherent categorization scheme |
US20070250576A1 (en) | 2006-04-21 | 2007-10-25 | Shruti Kumar | Method and system for automatically providing an abstract of a response message in a subject line of the response message |
US20090055481A1 (en) | 2007-08-20 | 2009-02-26 | International Business Machines Corporation | Automatically generated subject recommendations for email messages based on email message content |
US20090106650A1 (en) | 2007-10-23 | 2009-04-23 | International Business Machines Corporation | Customizing email subjects for subscription generated email messages |
US8645430B2 (en) | 2008-10-20 | 2014-02-04 | Cisco Technology, Inc. | Self-adjusting email subject and email subject history |
US20110154221A1 (en) | 2009-12-22 | 2011-06-23 | International Business Machines Corporation | Subject suggestion based on e-mail recipients |
US20120110432A1 (en) * | 2010-10-29 | 2012-05-03 | Microsoft Corporation | Tool for Automated Online Blog Generation |
US20130346511A1 (en) * | 2012-06-20 | 2013-12-26 | Comcast Cable Communications, Llc | Life management services |
US20140289344A1 (en) | 2013-03-07 | 2014-09-25 | Jeff CALHOUN | Digital notification enhancement system |
US9331965B2 (en) | 2013-08-23 | 2016-05-03 | International Business Machines Corporation | Automatically generating email subject lines |
US20150058426A1 (en) | 2013-08-23 | 2015-02-26 | International Business Machines Corporation | System and method for automatically generating email subject lines |
US9092742B1 (en) | 2014-05-27 | 2015-07-28 | Insidesales.com | Email optimization for predicted recipient behavior: suggesting changes in an email to increase the likelihood of an outcome |
US20160196561A1 (en) * | 2015-01-06 | 2016-07-07 | Adobe Systems Incorporated | Organizing and classifying social media conversations to improve customer service |
US20170177715A1 (en) * | 2015-12-21 | 2017-06-22 | Adobe Systems Incorporated | Natural Language System Question Classifier, Semantic Representations, and Logical Form Templates |
US20170295118A1 (en) * | 2016-04-11 | 2017-10-12 | Yahoo!, Inc. | Content subject suggestions |
US20190197107A1 (en) * | 2017-12-22 | 2019-06-27 | Microsoft Technology Licensing, Llc | AI System to Determine Actionable Intent |
US20200019609A1 (en) * | 2018-07-13 | 2020-01-16 | Asapp, Inc. | Suggesting a response to a message by selecting a template using a neural network |
EP3654258A1 (en) * | 2018-11-14 | 2020-05-20 | KBC Groep NV | Automated electronic mail assistant |
US20200193380A1 (en) * | 2018-12-14 | 2020-06-18 | International Business Machines Corporation | Detection and categorization of electronic communications |
US20210083998A1 (en) * | 2019-09-12 | 2021-03-18 | International Business Machines Corporation | Machine Logic Rules to Enhance Email Distribution |
Non-Patent Citations (2)
Title |
---|
"International Search Report and the Written Opinion Issued in PCT Application No. PCT/US2020/054894", dated Dec. 15, 2020, 12 Pages. |
Zhang, Rui, and Joel Tetreault. "This email could save your life: Introducing the task of email subject line generation." arXiv preprint arXiv:1906.03497 (2019). (Year: 2019). * |
Also Published As
Publication number | Publication date |
---|---|
CN114631094A (en) | 2022-06-14 |
US20210133287A1 (en) | 2021-05-06 |
WO2021086573A1 (en) | 2021-05-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10554590B2 (en) | Personalized automated agent | |
US11223584B2 (en) | Automatic action responses | |
US10713602B2 (en) | Aggregating enterprise graph content around user-generated topics | |
US11200269B2 (en) | Method and system for highlighting answer phrases | |
US11093711B2 (en) | Entity-specific conversational artificial intelligence | |
US10528632B2 (en) | Systems and methods for responding to an online user query | |
US11151166B2 (en) | Context-based multi-granularity intent discovery | |
US11899675B2 (en) | Machine reading comprehension system for answering queries related to a document | |
US11250839B2 (en) | Natural language processing models for conversational computing | |
US11935010B2 (en) | Intelligent subject line suggestions and reformulation | |
US20180157747A1 (en) | Systems and methods for automated query answer generation | |
US11354500B2 (en) | Artificial intelligence for identifying relevant content related to specific tasks | |
US11030537B2 (en) | Intelligent inferences of authoring from document layout and formatting | |
US20180196870A1 (en) | Systems and methods for a smart search of an electronic document | |
US20230135962A1 (en) | Training framework for automated tasks involving multiple machine learning models | |
WO2023014454A1 (en) | Context-aware observational entity recognition and capture | |
WO2023003675A1 (en) | Enterprise knowledge base system for community mediation | |
US20160232231A1 (en) | System and method for document and/or message document and/or message content suggestion, user rating and user reward | |
US20220405709A1 (en) | Smart Notifications Based Upon Comment Intent Classification | |
US20230004568A1 (en) | Multiple semantic hypotheses for search query intent understanding | |
US20210406270A1 (en) | Leveraging Interlinking Between Information Resources to Determine Shared Knowledge | |
EP4214624A1 (en) | Systems and methods for identifying entities and constraints in natural language input | |
US11900926B2 (en) | Dynamic expansion of acronyms in audio content |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: MICROSOFT TECHNOLOGY LICENSING, LLC, WASHINGTON Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:AYLOO, KALYAN;REEL/FRAME:050886/0141 Effective date: 20191031 |
|
FEPP | Fee payment procedure |
Free format text: ENTITY STATUS SET TO UNDISCOUNTED (ORIGINAL EVENT CODE: BIG.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: FINAL REJECTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NOTICE OF ALLOWANCE MAILED -- APPLICATION RECEIVED IN OFFICE OF PUBLICATIONS |
|
ZAAB | Notice of allowance mailed |
Free format text: ORIGINAL CODE: MN/=. |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: PUBLICATIONS -- ISSUE FEE PAYMENT VERIFIED |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |